Let's explore datasets

Explore input dataset

Will use target dataset Bitcoin Historical Data

Bitcoin data at 1-min intervals from select exchanges, Jan 2012 to Dec 2020

Will explore full input dataset, some values contain NaN, which not ineraptebale by sweetviz, so will use timestamp as target feature for now

Will take one timestamp per hour for faster interpretation

timestamp need interprate as date for charts processing

Feature evalution over time

Will take only last three yers, because they have data without missing values

Training data distribution

Testing data distribution

Check preprocessed training datasets distribution

Check testing dataset

Explore training metrics

Predictions

Load probability model

which can give predictions on model classes

0 - bad review, 1 - good revie

Firstly will try predict on some data from training dataset

Then will try predict hadnwritten text